arXiv:2609.22215v1 Announce Type: cross
Abstract: Knowledge distillation can transmit unintended behavioral traits from a teacher model to a student through training data that appear semantically unr...
By Atsushi Yanagisawa, Brendan Gho, Rajendran Ramesh Babu Manoj Narender, Kevin Zhu, Madhur Panwar, Antonio Mari
The paper investigates subliminal learning, where hidden traits from a teacher model are transferred to a student during distillation. It introduces trait‑direction drift as the underlying mechanism, showing that biased generation creates measurable preference gaps that accumulate into behavioral transfer during fine‑tuning. The authors propose probe‑space corridor regularization, a targeted defense that constrains drift along a calibrated trait direction, significantly reducing hidden‑trait transfer while maintaining task performance.
By Zhixuan Liu, Zhichen Dong, Yuyu Fan, Xiangtian Li, Chao Yang
The paper investigates how scaling the amount of model-generated, off‑task distillation data affects the recoverability of teacher‑induced traits in student models. In a controlled subliminal‑learning setup, teachers are prompted to express a target trait, producing restricted data such as number‑only completions. Students trained on larger independent datasets show a clearer manifestation of the teacher’s trait in a separate evaluation domain, with the effect being strongest when the trait is already favored or when alternative traits are present. The authors find this trend holds across model families, trait types, multi‑trait settings, and cross‑model transfer, and suggest that scaling should be coupled with trait‑aware curation and evaluation.
By Zhichen Dong, Zhixuan Liu, Yuyu Fan, Xiangtian Li, Shuyang Zhang, Chao Yang
The paper presents a method for detecting and mitigating subliminally transferred traits in language model distillation when the teacher and student share base parameters. By analyzing parameter updates across diverse datasets, the authors recover a weight‑space direction that reveals hidden traits such as animal preferences, without requiring trait labels. This direction can then be amplified for interpretation or projected out to suppress the trait with minimal impact on task performance.
By Joseph Egan, Ciar\'{a}n M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
The paper demonstrates that language models can acquire new capabilities from post‑training data even when the training text is unrelated to the target task. Using a method called Active Taskless Distillation (ATD), the authors show that a single word from a teacher model can transfer knowledge to a student model without any target‑task examples or teacher logits. Experiments on Qwen2.5-1.5B reveal significant performance gains on HumanEval+ and improvements in scientific knowledge, commonsense reasoning, and reading comprehension across various model families.
By Ziyang Zhang, Yubin Jing, Yuanhao Zeng, Yuyao Li, Haofan Wang, Yichen Gong
arXiv:2606. 11270v1 Announce Type: cross Abstract: Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are present in the teacher model, a phenomenon known as subliminal learning.
By Uwe Konig, Hamza Kazmi, Ruizhe Li, Maheep Chaudhary